{"slug":"brycewang-stanford-acl-reproducibility","source_name":"brycewang-stanford/acl-reproducibility","name":"Brycewang Stanford/Acl Reproducibility","description":"Use when strengthening reproducibility evidence for an ACL paper reviewed through ACL Rolling Review, covering the Responsible NLP checklist end to end, hyperparameter and compute reporting, prompt and decoding disclosure for LLM experiments, data contamination auditing, variance across runs, and checklist-to-paper consistency.","version":1,"lift":{"pass_rate_delta_pts":13.64,"pass_rate_pct":90.9,"total_cases":22,"passed_cases":20,"tokens_delta_pct":20.2,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-15T03:15:50.221802+00:00"},"skill_score":0.9091,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":13.64,"with_pass_pct":90.9,"without_pass_pct":77.3,"tokens_delta_pct":20.2,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-15T03:15:50.221802+00:00","run_id":"9b3b8949-ccab-47e3-a1ec-fa5c204bb409","version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"MIT","install_count":0,"manifest_hash":"c8dbd8bb6654c19b86935a1d4750ee31c651ecfb24716e31db731147cb1175e4","raw_url":"https://app.decimal.ai/s/brycewang-stanford-acl-reproducibility/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/brycewang-stanford-acl-reproducibility"}